Using AI to improve diagnosis and risk assessment for lung diseases

Deep Learning Diagnostic and Risk-stratification for Idiopathic Pulmonary Fibrosis and Chronic Obstructive Pulmonary Disease in Digital Lung Auscultations

This study is testing a new artificial intelligence tool to see if it can help doctors better diagnose and understand the risks of lung diseases like idiopathic pulmonary fibrosis, non-specific interstitial pneumonia, and chronic obstructive pulmonary disease.

Quick facts

• Study type: Observational
• Enrollment: 160 (estimated)
• Ages: 18 Years and up
• Sex: All
• Sponsor: Pediatric Clinical Research Platform (Academic / other)
• Drugs / interventions: immunotherapy
• Locations: 1 site (Sion, Wallis)
• Trial ID: NCT05318599 on ClinicalTrials.gov

What this trial studies

This study aims to develop an artificial intelligence algorithm to enhance the diagnosis and risk stratification of idiopathic pulmonary fibrosis (IPF), non-specific interstitial pneumonia (NSIP), and chronic obstructive pulmonary disease (COPD). It will involve a single-center, prospective, population-based case-control design, recruiting 120 patients with these lung conditions and 40 age-matched controls. Participants will undergo lung auscultation and lung ultrasound, with data collected to train the AI algorithm for accurate diagnostic predictions. The study will also assess the relationship between lung sounds and clinical characteristics to improve patient care.

Who should consider this trial

Good fit: Ideal candidates include adults aged 18 and older with diagnosed IPF, NSIP, or COPD.

Not a fit: Patients with severe cardiovascular disease, acute infectious pulmonary diseases, or asthma may not benefit from this study.

Why it matters

Potential benefit: If successful, this approach could lead to earlier and more accurate diagnoses of severe lung diseases, improving patient outcomes.

How similar studies have performed: Other studies have shown promise in using AI for diagnostic purposes in pulmonary diseases, indicating potential success for this approach.

Eligibility criteria

Inclusion Criteria:

* Written informed consent
* age \> 18 years old.
* patients with already-diagnosed IPF (group 1) prior to the consultation (index) date.
* patients with already-diagnosed NSIP (group 2) prior to the consultation (index) date.
* patients with already-diagnosed COPD (group 3) prior to the consultation (index) date.
* Control subjects must be followed-up at the pulmonology outpatient clinic for:

  1. obstructive sleep apnoea.
  2. occupational lung diseases (miners, chemical workers, etc.).
  3. pulmonary nodules (considered benign after 2 years).

Exclusion Criteria:

* patients who cannot be mobilized for posterior auscultation.
* patients known for severe cardiovascular disease with pulmonary repercussion.
* patients known for a concurrent, acute, infectious pulmonary disease (e.g., pneumonia, bronchitis).
* patients known for asthma.
* patients known or suspected of immunodeficiency, alpha-1-antitrypsin deficit, and or under immunotherapy.
* patients with physical inability to follow procedures.
* patients with inability to give informed consent.

Where this trial is running

Sion, Wallis

• Centre Hospitalier du Valais Romand — Sion, Wallis, Switzerland (Recruiting)

Study contacts

• Principal investigator: Pierre-Olivier Bridevaux, Prof. — Hôpital du Valais, Switzerland
• Study coordinator: Johan N. Siebert, MD

Conditions Lung; Disease, Interstitial, With Fibrosis; Pulmonary Disease, Chronic Obstructive; Artificial Intelligence; Disease, Interstitial, with Fibrosis; Idiopathic Pulmonary Fibrosis; Idiopathic Interstitial Pneumonias; Deep Learning